This is more related to the new MCP connector that has been released but I’m not sure where this ticket should be logged.
Basically, the MCP connector is unable to download vtt/txt files for meetings that DO have VTTs in the zoom portal. This is trivially easy via the api but is not possible via MCP despite the MCP being promoted as a tool that can download meeting resources etc.
```
GET https://api.zoom.us/v2/meetings/{meetingUuid}/transcript # returns metadata including the download_url
GET {download_url} — # the URL from above, fetches the actual VTT file content
```
Is there any way this can be added? For us this is a major missing feature and, after having waited a long time for Zoom to implement an MCP connector, we’ve had to build our own. But it would be nice if the official one did this so that we don’t have to implement auth and MCP infra ourselves.
@Luke7 this should be working. There might be additional settings within zoom.us which you need to turn on. needs to allow users/host to retain the transcript. I also enabled the setting for “Allow users to retain transcripts generated by meeting summary for use by other AI Companion services”
Hi Chun, thanks for looking into this. I think the issue may well be a permissions / config issue but I’m now wondering if this is actually a limitation of the MCP server.
Apologies, I don’t find the documentation very clear - there are lots of settings and some of the settings you listed above are not visible to me. Not sure if that is user config or jurisdictional thing?
Anyway, an example from today…
Background
I have a meeting which was not recorded - this is standard practice for us - but does have a VTT (.txt file) available in the zoom.us portal. I can download this vtt via the zoom website.
However, when I try to use the MCP connector to get hold of this VTT, I see the following response..
Please find this zoom meeting from yesterday…
's Zoom Meeting
Time: 9:25 AM – 9:30 AM UTC
Host:
Duration: ~5 minutes
Has AI summary: Yes
Perfect, please get the vtt transcript of that meeting.
The search results showed has_recording: false for that meeting, which means there’s no cloud recording — and without a recording, there won’t be a VTT transcript file either.
The meeting was only about 5 minutes long (9:25–9:30 AM), which may be why it wasn’t recorded. However, it did show has_summary: true, so there is an AI-generated summary available.
For the record, I can reliably download the VTT via the Zoom API so the API does support this. I’m just not sure why the MCP is gated by the has_recording flag.
